# 1. A little bit of theory

Between 291,000 and 646,000 people worldwide die from seasonal influenza-related respiratory illnesses each year. iF°EVE will change this. iF°EVE will be a life-saver like a defibrillator or a rescue helicopter. First we will take a look at the body core temperature classification:

Class | Body core temperature |

Hypothermia | < 35 °C |

Normal | 36.5-37.5 °C |

Fever | > 38.3 °C |

Hyperthermia | > 40.0 °C |

Hyperpyrexia | > 41.5 °C |

Easy to classify depending on the measured temperature only. Next we will take a look at the Naive Bayes classifiers that are commonly used in automatic medical diagnosis. There are many tutorials about the naive Bayes classifier out there, so I keep it short here.

Bayes' theorem:

*h*: Hypothesis*d*: Data

P(*h*): Probability of hypothesis *h* before seeing any data *d*

P(*d*|*h*): Probability of the data if the hypothesis *h* is true

The data evidence is given by

where P(*h*|*d*) is the probability of hypothesis *h* after having seen the data *d*.

Generally we want the most probable hypothesis given training data. This is the* maximum a posteriori hypothesis*:

*H*: Hypothesis set or space

As the denominators P(*d*) are identical for all hypotheses,* h**MAP* can be simplified:

If our data *d* has several attributes, the naïve Bayes assumption can be used. Attributes *a* that describe data instances are conditionally independent given the classification hypothesis:

Every human depending on the age catches a cold 3-15 times a year. Taking the average 9 times a year and assuming a world population of 7· 10^9, we have 63· 10^9 common cold cases a year. Around 5·10^6 people will get the flu per year. Now we can compute:

This means only one of approx. 12500 patients with common cold/flu like symptoms has actually flu! Rests of the data are taken from here. The probability-look-up table for supervised learning looks then as follows:

Prob | Flu | Common cold |

P(h) | 0.00008 | 0.99992 |

P(Fatigue|h) | 0.8 | 0.225 |

P(Fever|h) | 0.9 | 0.005 |

P(Chills|h) | 0.9 | 0.1 |

P(Sore throat|h) | 0.55 | 0.5 |

P(Cough|h) | 0.9 | 0.4 |

P(Headache|h) | 0.85 | 0.25 |

P(Muscle pain|h) | 0.675 | 0.1 |

P(Sneezing|h) | 0.25 | 0.9 |

Therefore:

Note: The probability that an event *A* is not occurring is given by

Multiplying a lot of probabilities, which are between 0 and 1 by definition, can result in floating-point underflow. Since

it is better to perform all computations by summing logs of probabilities rather than multiplying probabilities. The class with highest final un-normalized log probability score is still the most probable:

# 2. Schematic

Below you will find the initial schematic (right click, view image to enlarge).

Body temperature measurement is done by the infrared thermometer MLX90614ESF-DCA. Temperature code *E* means -40°C to 85°C, package code *SF* means TO-39 package and option code...

I am curious whether this device is wearable. I mean like a watch or bracelet. Besides, are environmental factors taken into account in your calculation?

Anyway I think it's a great idea and look forward to more updates.